Routes 3D ResNets PyTorch video action-recognition workflows across training, inference, and data preparation.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use the Folding@home coronavirus repository conventions to curate molecular structures, prepare bounded OpenMM systems, and preserve target, publication, and provenance notes.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
설치 방법 보기설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.
Use this repo-specific operating skill for reusable work derived from the Folding@home coronavirus preparation repository. It covers structure curation, OpenMM preparation/equilibration mechanics, and project-context notes. It does not run Folding@home clients, network acquisition, long production trajectories, or medical/therapeutic interpretation.
For a new simulation input, establish source-structure identity and note provenance first; curate and validate the coordinate topology; choose and document the force-field/ligand parameter path; prepare a small CPU OpenMM system; run only a bounded minimization/equilibration smoke check; inspect energy, atom count, box, and output bundle; then record exact parameters, versions, warnings, and limitations. A later Researcher may expand the run only with an explicit scientific and compute budget.
Do not treat a filename, a successful PDB parse, a short CPU step, or XML serialization as proof of biological identity, force-field suitability, stable long-timestep dynamics, binding, efficacy, or reproducibility across platforms.
The source project documents rapidly prepared inputs and commonly uses equilibrated_4fs.pdb as the Folding@home handoff. Reusable generated helpers use safer explicit arguments and short defaults instead of historical hard-coded paths or multi-nanosecond defaults. A 4 amu hydrogen mass and 4/5 fs continuation are historical workflow conventions that must be disclosed and validated for the actual system, not universal recommendations.
The required backend for this selected scope is CPU OpenMM. CUDA is optional: platform enumeration succeeded in inspection, but context creation was limited by CUDA_ERROR_UNSUPPORTED_PTX_VERSION. Do not claim CUDA verification or require it for a CPU result.
Use repo-provenance.md to anchor claims to the source revision and evidence paths. This generated skill is intentionally left in the repository-local output tree and is not imported into the managed DisCo skill library.
아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.
로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.
아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.
Routes 3D ResNets PyTorch video action-recognition workflows across training, inference, and data preparation.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Guide 3DDFA Python inference, geometry rendering, training/evaluation, and optional C++ ONNX workflows for 3D dense face alignment.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Routes 3DDFA_V2 face-alignment setup, still-image demos, video tracking, and ONNX benchmarking workflows.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Operate AB3DMOT 3D multi-object tracking workflows for KITTI and nuScenes data, tracking, evaluation, and visualization.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use Hugging Face Accelerate for PyTorch training-loop migration, distributed launch/configuration, DeepSpeed/FSDP/TPU backend setup, big-model inference/offload, checkpointing, tracking, and troubleshooting.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Route Acme reinforcement-learning framework tasks across core loops, replay/data, JAX agents, and TensorFlow/Sonnet agents.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.